@article {13740, title = {Combining outputs from multiple machine translation systems}, journal = {Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Proceedings of the Main Conference}, year = {2007}, month = {2007///}, pages = {228 - 235}, abstract = {Currently there are several approaches tomachine translation (MT) based on differ- ent paradigms; e.g., phrasal, hierarchical and syntax-based. These three approaches yield similar translation accuracy despite using fairly different levels of linguistic knowledge. The availability of such a variety of systems has led to a growing interest toward finding better translations by combining outputs from multiple sys- tems. This paper describes three differ- ent approaches to MT system combina- tion. These combination methods oper- ate on sentence, phrase and word level exploiting information from N -best lists, system scores and target-to-source phrase alignments. The word-level combination provides the most robust gains but the best results on the development test sets (NIST MT05 and the newsgroup portion of GALE 2006 dry-run) were achieved by combining all three methods. }, author = {Rosti,A.V.I. and Ayan,N.F. and Xiang,B. and Matsoukas,S. and Schwartz,R. and Dorr, Bonnie J} }